CERN Accelerating science

Talk
Title Learning to discover: machine learning in high-energy physics
Video
If you experience any problem watching the video, click the download button below
Download Embed
Mp4:Medium
(1000 kbps)
High
(4000 kbps)
More..
Copy-paste this code into your page:
Copy-paste this code into your page to include both slides and lecture:
Author(s) Kégl, Balázs (speaker) (LAL/LRI-Orsay, FR)
Corporate author(s) CERN. Geneva
Imprint 2014-05-13. - Streaming video.
Series (EP Seminar)
Lecture note on 2014-05-13T11:00:00
Subject category EP Seminar
Abstract In this talk we will survey some of the latest developments in machine learning research through the optics of potential applications in high-energy physics. We will then describe three ongoing projects in detail. The main subject of the talk is the data challenge we are organizing with ATLAS on optimizing the discovery significance for the Higgs to tau-tau channel. Second, we describe our collaboration with the LHCb experiment on designing and optimizing fast multi-variate techniques that can be implemented as online classifiers in triggers. Finally, we will sketch a relatively young project with the ILC (Calice) group in which we are attempting to apply deep learning techniques for inference on imaging calorimeter data.
Copyright/License © 2014-2024 CERN
Submitted by guillaume.unal@cern.ch

 


 Record created 2014-05-19, last modified 2022-11-02


External link:
Download fulltext
Event details